With OCR working ver 1

app.py

@@ -1,10 +1,40 @@
+from pdf2image import   convert_from_path
+from PIL import Image   
+import pytesseract
 import gradio as gr
-import sys
 
-def greet(name):
-    python_version = sys.version.split()[0]
+def tesseract_ocr(filepath: str):
+    """
+    Perform OCR on the given image file and return the extracted text.
+    """
+    # Open the image file
+    with Image.open(filepath) as img:
+        # Use pytesseract to do OCR on the image
+        text = pytesseract.image_to_string(img)
+    return text 
+
+title = "Invoicer IA"
+description = "extract data from invoice"
+article = "This is a simple OCR application that extracts text from images using Tesseract OCR. You can upload an image of an invoice, and the application will return the extracted text."
+examples = [["example_invoice.png"]]  
+
+
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f'<h1 style="text-align: center; margin-bottom: 1rem;">{title}</h1>')
+    gr.Markdown(description)
+    gr.Markdown(article)
+
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(type="filepath", label="Upload Invoice Image")
+            output_text = gr.Textbox(label="Extracted Text", lines=10, placeholder="Extracted text will appear here...")
+
+        with gr.Column():
+            submit_button = gr.Button("Submit")
+    
     
-    return f"Hello {name}!!\nPython version: {python_version}"
+    submit_button.click(fn=tesseract_ocr, inputs=image_input, outputs=output_text)
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()
+    

packages.txt

@@ -0,0 +1 @@
+tesseract-ocr-all

requirements.txt

@@ -1,54 +1,3 @@
-aiofiles==23.2.1
-annotated-types==0.7.0
-anyio==4.9.0
-certifi==2025.1.31
-charset-normalizer==3.4.1
-click==8.1.8
-colorama==0.4.6
-fastapi==0.115.12
-ffmpy==0.5.0
-filelock==3.18.0
-fsspec==2025.3.2
-gradio==5.23.3
-gradio_client==1.8.0
-groovy==0.1.2
-h11==0.14.0
-httpcore==1.0.7
-httpx==0.28.1
-huggingface-hub==0.30.1
-idna==3.10
-Jinja2==3.1.6
-markdown-it-py==3.0.0
-MarkupSafe==3.0.2
-mdurl==0.1.2
-numpy==2.2.4
-orjson==3.10.16
-packaging==24.2
-pandas==2.2.3
-pillow==11.1.0
-pydantic==2.11.2
-pydantic_core==2.33.1
-pydub==0.25.1
-Pygments==2.19.1
-python-dateutil==2.9.0.post0
-python-multipart==0.0.20
-pytz==2025.2
-PyYAML==6.0.2
-requests==2.32.3
-rich==14.0.0
-ruff==0.11.4
-safehttpx==0.1.6
-semantic-version==2.10.0
-shellingham==1.5.4
-six==1.17.0
-sniffio==1.3.1
-starlette==0.46.1
-tomlkit==0.13.2
-tqdm==4.67.1
-typer==0.15.2
-typing-inspection==0.4.0
-typing_extensions==4.13.1
-tzdata==2025.2
-urllib3==2.3.0
-uvicorn==0.34.0
-websockets==15.0.1
+gradio
+pytesseract
+pdf2image